ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-07 04:20:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge mainline llama.cpp (#3)

Browse Source 
* Merging mainline - WIP

* Merging mainline - WIP

AVX2 and CUDA appear to work.
CUDA performance seems slightly (~1-2%) lower as it is so often
the case with llama.cpp/ggml after some "improvements" have been made.

* Merging mainline - fix Metal

* Remove check

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2024-07-27 07:55:01 +02:00
committed by GitHub
parent 0684c3e9c7
commit 154e0d75fc
612 changed files with 50817 additions and 165936 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
tests/test-tokenizer-0.cpp
View File

@@ -195,11 +195,11 @@ int main(int argc, char **argv) {
const bool add_special = false;
for (const auto & test_kv : k_tests) {
const std::vector<llama_token> res = llama_tokenize(ctx, test_kv.first, add_special);
const std::vector<llama_token> res = llama_tokenize(ctx, test_kv.first, add_special, false);
printf("\n");
printf("src: '%s'\n", test_kv.first.c_str());
printf("res: '%s'\n", llama_detokenize_bpe(ctx, res).c_str());
printf("res: '%s'\n", llama_detokenize(ctx, res).c_str());
printf("tok: ");
for (const auto & tok : res) {
printf("%d ", tok);
@@ -216,8 +216,8 @@ int main(int argc, char **argv) {
if (!correct) {
fprintf(stderr, "%s : failed test: '%s'\n", __func__, test_kv.first.c_str());
fprintf(stderr, "%s : detokenized to: '%s' instead of '%s'\n", __func__,
llama_detokenize_bpe(ctx, res).c_str(),
llama_detokenize_bpe(ctx, test_kv.second).c_str());
llama_detokenize(ctx, res).c_str(),
llama_detokenize(ctx, test_kv.second).c_str());
fprintf(stderr, "%s : expected tokens: ", __func__);
for (const auto & t : test_kv.second) {
fprintf(stderr, "%6d '%s', ", t, llama_token_to_piece(ctx, t).c_str());
@@ -253,7 +253,7 @@ int main(int argc, char **argv) {
{
const auto t_start = ggml_time_us();
res = llama_tokenize(ctx, text, add_special);
res = llama_tokenize(ctx, text, add_special, false);
const auto t_end = ggml_time_us();
@@ -272,7 +272,7 @@ int main(int argc, char **argv) {
}
for (const auto & tok : res) {
//ofs << tok << " '" << string_strip(llama_detokenize_bpe(ctx, std::vector<int>{tok})) << "'" << std::endl;
//ofs << tok << " '" << string_strip(llama_detokenize(ctx, std::vector<int>{tok})) << "'" << std::endl;
ofs << tok << "\n";
}
}